
"""
@author: Tugba Eraslanoglu

Checking the data to map event area coordinates 

"""

import pandas as pd
import geopandas as gpd
import folium
from pyproj import CRS

/tmp/ipykernel_188/394615755.py:9: UserWarning: Shapely 2.0 is installed, but because PyGEOS is also installed, GeoPandas will still use PyGEOS by default for now. To force to use and test Shapely 2.0, you have to set the environment variable USE_PYGEOS=0. You can do this before starting the Python process, or in your code before importing geopandas:

import os
os.environ['USE_PYGEOS'] = '0'
import geopandas

In a future release, GeoPandas will switch to using Shapely by default. If you are using PyGEOS directly (calling PyGEOS functions on geometries from GeoPandas), this will then stop working and you are encouraged to migrate from PyGEOS to Shapely 2.0 (https://shapely.readthedocs.io/en/latest/migration_pygeos.html).
  import geopandas as gpd


#Load the data and read
#data_file = "ACLED_newspaperdata.csv"
data_file = "newspaperdata.csv"
#df = pd.read_csv(data_file, delimiter=';')
df = pd.read_csv(data_file, sep='\t')
df.head()


# Check the columns of the data
df.columns

Index(['Unnamed: 0', 'event_id', 'event_date', 'year', 'month',
       'disorder_type', 'event_type', 'sub_event_type', 'actor1',
       'assoc_actor_1', 'inter1', 'actor2', 'assoc_actor_2', 'inter2',
       'interaction', 'civilian_targeting', 'admin2', 'location', 'latitude',
       'longitude', 'source', 'source_scale', 'label', 'class', 'notes22',
       'notes', 'fatalities', 'timestamp', 'population_1km', 'population_2km',
       'population_5km', 'population_best', 'crowd_size_class',
       'crowd_size_cat', 'crowd_size', 'crowd_size_w_n', 'with_vehicles', '?',
       'split', 'notes11'],
      dtype='object')


# Check the unique longitutude values of the data
df['longitude'].unique()

array([13.4024, 13.4403, 13.4354, 13.3738, 13.2317, 13.5876, 13.4951,
       13.2639, 13.3459, 13.4105, 13.6006, 13.4031, 13.198 ])


# Check the unique latitude values of the data
df['latitude'].unique()

array([52.5177, 52.501 , 52.481 , 52.4406, 52.428 , 52.5223, 52.5197,
       52.5079, 52.5711, 52.5244, 52.4175, 52.566 , 52.5356])


df['longitude'] = pd.to_numeric(df['longitude'])
df['latitude'] = pd.to_numeric(df['latitude'])


# Create a new GeoDataFrame
df_geo = gpd.GeoDataFrame(df, geometry=gpd.points_from_xy(df['longitude'], df['latitude']))


# Set the CRS to WGS84 (EPSG:4326)
df_geo.crs = CRS("EPSG:4326")


# Create a Folium map centered around the mean latitude and longitude
osm_map = folium.Map(location=[df_geo['latitude'].mean(), df_geo['longitude'].mean()], zoom_start=4)


# Convert the GeoDataFrame to GeoJSON format
points = folium.features.GeoJson(df_geo.to_json())


# Add the GeoJSON data to the map
osm_map.add_child(points)
osm_map

	Unnamed: 0	event_id	event_date	year	month	disorder_type	event_type	sub_event_type	actor1	assoc_actor_1	...	population_5km	population_best	crowd_size_class	crowd_size_cat	crowd_size	crowd_size_w_n	with_vehicles	?	split	notes11
0	1	DEU20172	2024-02-16	2024	2	Demonstrations	Protests	Peaceful protest	Protesters (Germany)	NaN	...	138680	23736	3	NaN	100.0	100.0	NaN	NaN	NaN	about 100 climate activists participated in a ...
1	2	DEU20173	2024-02-16	2024	2	Demonstrations	Protests	Peaceful protest	Protesters (Germany)	NaN	...	138680	23736	6	NaN	1020.0	1020.0	NaN	NaN	NaN	in the evening, about 1,000 people participate...
2	3	DEU20104	2024-02-15	2024	2	Demonstrations	Protests	Protest with intervention	Protesters (Germany)	Last Generation (Germany)	...	138680	23736	1	NaN	3.0	3.0	NaN	NaN	NaN	3 Last Generation activists protested in the F...
3	4	DEU20126	2024-02-15	2024	2	Demonstrations	Protests	Peaceful protest	Protesters (Germany)	Labor Group (Germany)	...	138680	23736	0	NaN	200.0	NaN	NaN	NaN	NaN	actors and directors protested in Berlin - Mit...
4	5	DEU20100	2024-02-14	2024	2	Demonstrations	Protests	Protest with intervention	Protesters (Germany)	NaN	...	127378	11620	4	NaN	280.0	280.0	NaN	NaN	NaN	in the evening, about 230 pro-Palestine demons...